Applied & Human-Centered · Computer Science & AI
Software Engineering
The newest papers in Software Engineering that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
1,466 papers, from 31 August 2026 to 5 November 2026: 1,451 arXiv preprints and 15 OpenAlex records.
Get the few papers worth your time in Software Engineering every morning.
Follow Software Engineering and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 37
Understanding and Mitigating Cross-Session Attacks via Persistent Artifacts in Agent Skill Composition
Agent skills extend the capabilities of AI agents by bundling instructions, code, and resources into reusable packages.Agent4Spec: An LLM-based Agentic System to Optimize API Specifications through Automated Validation and Market Analysis
API specifications serve as critical documentation for modern software development, directly impacting integration efficiency and client code generation.AgentSWE: Can Coding Agents Build the Agent You Actually Want?
As the production of software passes into the hands of software itself, coding agents are increasingly commissioned to build agents fitted to their users' own workflows.ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents
Coding agents are increasingly used to build programs from scratch as software engineers do rather than to resolve issues within a repository or to generate a repository from a given requirements…REINS: Agent-guided Thread Scheduling for Concurrency Bug Detection and Reproduction
Concurrency bugs manifest only under specific thread interleavings, making them hard to detect and reproduce.Not All Correct Fixes Run Alike: An Empirical Study of Patch Performance in Repository-Level Issue Resolution
Repository-level issue-resolution benchmarks such as SWE-bench evaluate submitted patches primarily based on whether they pass the correctness tests, leaving the runtime performance of different…SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle
Large Language Models (LLMs) are increasingly used throughout the software development lifecycle.A-SAW: The Agentic Software Architecture Workflow
AI assistance in software engineering focuses on implementation and verification, leaving the design phase, and in particular the maintenance of architecture documentation, comparatively underserved.(When) Should a Software Factory be Lights-off? Benchmarking Code Review Agents on Bug Detection
With the advances of coding agents, software developers are spending more time reviewing code than writing code.A Baseline Assessment for the Agentic Web Technology Stack
The fast pace in which protocols, frameworks, and technologies are being proposed for LLM-based agents results in a complex scenario for anyone aiming to create state-of-the-art AI solutions.MARGoS: A Configuration-Driven Platform for Reproducible MARL Experiments in ARGoS
Multi-agent reinforcement learning (MARL) has become a prominent research direction, particularly within collective robotics, where the ARGoS simulator is widely used to study emergent swarm behavior.Returning to Development States: When Full Sandbox Snapshots Help Coding Agents
Coding agents often make useful progress before they fail, but retry-from-scratch discards the machine state created along the way.Conserved amount, negotiable placement. Prompting perturbs one architecture, an AI reviewer both
Tesler's conservation law holds that a problem carries an irreducible amount of complexity.OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools
We introduce OpenMobile-2, a near-frontier mobile agent with fully open training environments and recipes.Agentic Evolution of SQL Test Generators
Automated testing has uncovered many logic bugs in Database Management Systems (DBMSs).AutoEnvScaling: Automating the Data Flywheel with Terminal Agents
Terminal agents solve tasks in software engineering and scientific research by executing commands in a terminal.Unconstrained CTI-REALM with Open-Weights
Organisations that want language-model agents for security work face a choice between open-weight models, which they can run and audit themselves, and far more expensive closed frontier models.Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules
Coding agents such as Claude Code also follow text files that developers write for them: a project file, skills the agent may choose to open, and rules that load automatically when the agent reads…Diagnosing Generalization Boundaries in AI-Based Vulnerability Detection via Calibrated Embedding Distances
High benchmark scores in learning-based vulnerability detection mask severe degradation under distribution shifts.Which Metadata Matters for LLM Tool Selection in MCP? Evidence from Controlled Factor-Level Interventions
In Model Context Protocol (MCP) systems, LLMs select tools from metadata rather than from their implementations.